English

Learning Correspondence Structures for Person Re-identification

Computer Vision and Pattern Recognition 2023-07-19 v3 Artificial Intelligence Multimedia

Abstract

This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure which indicates the patch-wise matching probabilities between images from a target camera pair. The learned correspondence structure can not only capture the spatial correspondence pattern between cameras but also handle the viewpoint or human-pose variation in individual images. We further introduce a global constraint-based matching process. It integrates a global matching constraint over the learned correspondence structure to exclude cross-view misalignments during the image patch matching process, hence achieving a more reliable matching score between images. Finally, we also extend our approach by introducing a multi-structure scheme, which learns a set of local correspondence structures to capture the spatial correspondence sub-patterns between a camera pair, so as to handle the spatial misalignments between individual images in a more precise way. Experimental results on various datasets demonstrate the effectiveness of our approach.

Keywords

Cite

@article{arxiv.1703.06931,
  title  = {Learning Correspondence Structures for Person Re-identification},
  author = {Weiyao Lin and Yang Shen and Junchi Yan and Mingliang Xu and Jianxin Wu and Jingdong Wang and Ke Lu},
  journal= {arXiv preprint arXiv:1703.06931},
  year   = {2023}
}

Comments

IEEE Trans. Image Processing, vol. 26, no. 5, pp. 2438-2453, 2017. The project page for this paper is available at http://min.sjtu.edu.cn/lwydemo/personReID.htm arXiv admin note: text overlap with arXiv:1504.06243

R2 v1 2026-06-22T18:51:35.166Z